© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 50972
    Prev
    Next
    INDEX
    Explanations

    article or Art

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mere
    -0.09
    æ¼Ķ
    -0.09
    .DisplayMember
    -0.09
    æIJĢ
    -0.09
    oses
    -0.08
     Reign
    -0.08
     DVR
    -0.08
    ç»°
    -0.08
    ä¸Ģæµģ
    -0.08
    æĦīå¿«
    -0.08
    POSITIVE LOGITS
    第
    0.10
     clause
    0.09
    å®ĹæŨ
    0.09
    usp
    0.09
    æĿ¡æ¬¾
    0.09
     sponsor
    0.09
    åİŁåĪĻ
    0.09
    åįģä¸īæĿ¡
    0.09
    clause
    0.09
    第ä¸ĢæĿ¡
    0.09
    Activations Density 0.020%

    No Known Activations